Blood-permeable bubble detection device and method

Through the image recognition technology and multi-module design of the hemopermeable bubble detection device, the accuracy and efficiency of bubble detection in blood purification treatment are solved, the safety of patients is ensured, and the accurate measurement and early warning function of bubble volume is realized.

CN118903587APending Publication Date: 2024-11-08GUANGDONG UNIV OF TECH

Patent Information

Application Number
CN202410936686.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-12
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The bubbles produced during blood purification treatment may lead to complications such as gas embolism and blood vessel blockage, posing a serious threat to the health and safety of patients.

Method used

A hemopermeable bubble detection device is designed, including an injection device, a blood circulation device and a bubble detection device. Using image recognition technology, it accurately identifies and measures bubbles through modules such as area segmentation, corrosion and expansion processing, minimum external rectangle generation and edge detection. and an alarm will be issued when the bubble volume exceeds the standard and the detection process will be interrupted.

Benefits of technology

It significantly improves the accuracy and efficiency of bubble detection in hemodialysis treatment, ensures the safety of patients' lives, and avoids medical risks caused by excessive bubbles.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118903587A_ABST
    Figure CN118903587A_ABST
Patent Text Reader

Abstract

The invention relates to a blood bubble detection device, device, equipment and medium, and the method comprises an injection device which is connected with a blood circulation device and comprises a plurality of injection pumps and check valves, and blood is injected into the blood circulation device through the injection pumps; the blood circulation device comprises a closed container and a heater; the bubble detection device is connected with the blood circulation device and comprises a test pipeline, pipeline control valves and a camera; and the central processing module is connected with the camera and is used for inputting the image data of the to-be-detected blood into a blood vapor bubble detection module of the central processing module so as to detect the blood vapor bubble volume of the to-be-detected blood in the test pipeline. The accuracy and efficiency of bubble detection in hemodialysis treatment can be remarkably improved, and the life safety of a patient is guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of medical equipment, and in particular to a hemodialysis bubble detection device and method. Background Art

[0002] Blood purification therapy, as a key medical treatment for chronic renal failure and other related diseases, may produce bubbles during the treatment process due to various factors. If these bubbles are not detected and removed in time, they may cause a variety of complications including gas embolism and vascular blockage, posing a serious threat to the health and safety of patients. In addition, the presence of bubbles may disrupt the normal blood flow pattern and affect the efficacy of hemodialysis.

[0003] In summary, the bubbles generated during blood purification treatment in the prior art may cause a variety of complications including gas embolism and vascular blockage, posing a serious threat to the health and safety of patients. The applicant has made corresponding explorations to solve this problem. Summary of the invention

[0004] The purpose of the present application is to solve the above-mentioned problems and to provide a hemodialysis bubble detection device and method.

[0005] In order to meet the various objectives of this application, this application adopts the following technical solutions:

[0006] A hemodialysis bubble detection device proposed to meet one of the purposes of this application comprises:

[0007] An injection device, the injection device is connected to the blood circulation device, and comprises a plurality of injection pumps and a check valve, and blood is injected into the blood circulation device through the injection pump;

[0008] The blood circulation device comprises a sealed container and a heater, wherein the sealed container is used to store the blood to be tested, and the heater is used to stir the blood to simulate blood flow and heat the blood to maintain the temperature of the blood to be tested;

[0009] The bubble detection device is connected to the blood circulation device, and comprises a test pipeline, various pipeline control valves and a camera. The corresponding test pipeline for storing the blood to be tested is selected by controlling the pipeline control valve, and the camera is used to obtain image data of the blood to be tested in the test pipeline;

[0010] A central processing module is connected to the camera and is used to input the image data of the blood to be tested into the hemodialysis bubble detection module of the central processing module to detect the volume of the hemodialysis bubbles of the blood to be tested in the test pipeline.

[0011] Optionally, the injection device includes a first injection pump and a second injection pump, the first injection pump is used to inject air, and the second injection pump is used to inject dialysate and anticoagulant.

[0012] Optionally, the bubble detection device includes four test pipelines and two cameras, the first test pipeline and the second test pipeline are the first group of test pipelines, and the third test pipeline and the fourth test pipeline are the second group of test pipelines, wherein the test pipelines are equipped with pipeline control valves, the upper and lower valves of each group of test pipelines are linked and controlled, and each camera shoots two test pipelines in the same group.

[0013] Optionally, the camera is disposed on a fixed bracket and is provided with a positioning mechanism module to ensure that the relative position and angle between the camera and the test pipeline remain unchanged during the shooting process.

[0014] Optionally, the hemodialysis bubble detection device further includes:

[0015] The alarm module is used to send a blood bubble excessively large warning to the display module when it detects that the volume of bubbles in the blood to be detected is greater than a preset volume threshold.

[0016] Optionally, the hemodialysis bubble detection module includes:

[0017] A region segmentation module, which is used to select a region of interest of the blood to be tested in the test tube;

[0018] A binarization processing module, which is used to filter out the contours corresponding to the hemodialysis bubbles in the image of the region of interest;

[0019] A corrosion processing module, which is used to remove non-bubble intervention factors within the contour corresponding to the hemodialysis bubble;

[0020] An expansion processing module, which is used to fill the hole at the edge of the contour corresponding to the hemodialysis bubble to ensure that the area containing the hemodialysis bubble is completely selected;

[0021] A minimum circumscribed matrix generation module, which is used to generate a minimum circumscribed rectangle of an area containing the hemodialysis bubble;

[0022] An edge detection module, which is used to determine the upper boundary edge point and the lower boundary edge point of the minimum circumscribed rectangle, and connect the detected edge points into lines to determine the upper boundary and the lower boundary of the hemodialysis bubble accumulation;

[0023] A bubble volume determination module is used to determine the stacking height of the hemodialysis bubbles in the test pipeline according to the maximum value of the ordinate in the lower boundary edge point of the minimum circumscribed rectangle and the minimum value of the ordinate in the upper boundary edge point, and determine the volume of the hemodialysis bubbles based on the stacking height and the specific specifications of the test pipeline.

[0024] A hemodialysis bubble detection method provided for another purpose of the present application is applied to the above-mentioned hemodialysis bubble detection device, comprising:

[0025] The central processing module acquires the blood image to be detected, and performs region segmentation based on the hemodialysis bubble detection model preset in the hemodialysis bubble detection module to determine the region of interest in the blood image to be detected;

[0026] Determine a preset grayscale threshold, and divide the image pixels corresponding to the region of interest in the blood image to be detected into a foreground and a background according to the preset grayscale threshold, so as to determine the contour corresponding to the hemodialysis bubble, wherein the foreground represents the hemodialysis bubble, and the background represents the blood and the dialysate;

[0027] Performing erosion and expansion operations on the contour corresponding to the hemodialysis bubble to eliminate small white noise points in the image and fill the holes at the edge of the bubble to determine the hemodialysis bubble area image;

[0028] Calculating and determining the minimum circumscribed rectangle corresponding to the hemodialysis bubble area image, and generating a virtual caliper for measuring boundary edge points;

[0029] Determine the ordinates of the lower boundary edge points and the upper boundary edge points corresponding to the minimum circumscribed rectangle based on the virtual caliper, calculate and determine the difference between the maximum ordinate of the lower boundary edge points and the minimum ordinate of the upper boundary edge points corresponding to the minimum circumscribed rectangle, and determine the stacking height of the hemodialysis bubbles in the test pipeline according to the difference;

[0030] Based on the stacking height of the hemodialysis bubbles in the test pipeline and the specific specifications of the test pipeline, the volume of the hemodialysis bubbles is calculated and determined to complete the detection of the hemodialysis bubbles.

[0031] Optionally, after the step of calculating and determining the volume of the hemodialysis bubbles based on the stacking height of the hemodialysis bubbles in the test pipeline and the specific specifications of the test pipeline, the method further includes:

[0032] In response to the alarm detection instruction, the volume of the hemodialysis bubble is obtained, and whether the volume of the hemodialysis bubble exceeds the preset volume threshold is detected. If exceeded, a bubble excessive warning signal is pushed to the display module to emit a flashing red light, and the pipeline control valve is controlled to be closed to cut off the blood circulation in the test pipeline to ensure the safety of the treatment process.

[0033] Optionally, the step of calculating and determining the minimum circumscribed rectangle corresponding to the hemodialysis bubble area image and generating a virtual caliper for measuring boundary edge points includes:

[0034] Determine the minimum circumscribed matrix corresponding to the bubble area based on the bubble area image, and use the upper boundary and the lower boundary of the minimum circumscribed matrix as reference edges, which correspond to the upper boundary and the lower boundary of the hemodialysis bubble respectively;

[0035] A plurality of rectangular handles are generated along the reference edge, and the rectangular handles are used as virtual calipers to identify and measure edge points on the upper and lower boundaries of the hemodialysis bubble.

[0036] Optionally, after the step of generating a plurality of rectangular handles along the reference edge and using the rectangular handles as virtual calipers to identify and measure edge points on the upper and lower boundaries of the hemodialysis bubble, the method further comprises:

[0037] The virtual caliper identifies and measures the edge points on the upper and lower boundaries of the blood bubble, and stores the edge points in an array, in which a search is performed to identify the minimum value of the vertical coordinate among all the upper boundary edge points and the maximum value of the vertical coordinate among all the lower boundary edge points.

[0038] Compared with the prior art, the present application aims to solve the problem that bubbles generated in blood purification treatment in the prior art may cause various complications including gas embolism and vascular blockage, which pose a serious threat to the health and safety of patients. The present application includes but is not limited to the following beneficial effects:

[0039] First, the hemodialysis bubble detection device of the present application is mainly composed of an injection device, a blood circulation device, a bubble detection device and a central processing module. It cooperates with the hemodialysis bubble detection model in the central processing module to work together to complete the detection and analysis of bubbles. The present application significantly improves the accuracy and efficiency of bubble detection in hemodialysis treatment and ensures the life safety of patients. The hemodialysis bubble detection device realizes the accurate identification and measurement of bubbles in the blood to be tested through the designed injection device, blood circulation device, bubble detection device and computer. The hemodialysis bubble detection device adopts image recognition technology, and effectively screens and quantifies the bubble area from the blood image to be tested through the modules such as region segmentation, binarization processing, corrosion and expansion processing, minimum circumscribed rectangle generation and edge detection in the hemodialysis bubble detection model. In addition, the built-in calibration module of the hemodialysis bubble detection device ensures the high accuracy of bubble volume measurement, and the design of the early warning module promptly issues an alarm and interrupts the detection process when the bubble volume exceeds the standard, thereby effectively avoiding possible medical risks.

[0040] Secondly, the hemodialysis bubble detection method of the present application adopts a multi-module design, and performs operations such as region segmentation, binarization processing, corrosion and expansion processing, minimum circumscribed rectangle generation and edge detection to accurately identify and quantify the bubble area. By identifying and quantifying the bubble area, the volume of the hemodialysis bubble in the test pipeline is determined to avoid the occurrence of safety accidents caused by excessive hemodialysis bubbles and avoid endangering the life safety of patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0042] Figure 1 Schematic diagram of the structure of the hemodialysis bubble detection device in the embodiment of the present application;

[0043] Figure 2 A functional block diagram of a hemodialysis bubble detection device provided in an embodiment of the present application;

[0044] Figure 3 A flowchart of the working process of the hemodialysis bubble detection device according to an embodiment of the present application;

[0045] Reference numerals: 1 first injection pump, 2 second injection pump, 3 sealed container, 4 heater, 5 pipeline control valve, 6 test tube, camera 7. DETAILED DESCRIPTION

[0046] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present application.

[0047] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0048] Unless expressly specified, one or more technical features of the present application can be deployed on a server for implementation and accessed by a client through a remote call to obtain an online service interface provided by the server, or can be directly deployed and run on a client for access.

[0049] The neural network models referenced or may be referenced in this application, unless expressly specified, can be deployed on a remote server and remotely called on the client, or can be deployed and directly called on a client with sufficient device capabilities. In some embodiments, when it runs on the client, its corresponding intelligence can be obtained through transfer learning to reduce the requirements for the client's hardware operating resources and avoid excessive occupation of the client's hardware operating resources.

[0050] Unless explicitly specified, the various data involved in this application can be stored remotely on a server or on a local terminal device, as long as it is suitable for being called by the technical solution of this application.

[0051] Those skilled in the art should be aware that, although the various methods of the present application are described based on the same concept and thus present commonality to each other, unless otherwise specified, these methods can be independently executed. Similarly, for each embodiment disclosed in the present application, they are all proposed based on the same inventive concept, therefore, concepts with the same expression, and concepts that are appropriately changed for convenience despite different expressions, should be understood as equivalent.

[0052] Unless the mutually exclusive relationship between the embodiments to be disclosed in this application is explicitly stated, the relevant technical features involved in each embodiment can be cross-combined to flexibly construct a new embodiment, as long as such combination does not deviate from the creative spirit of this application and can meet the needs of the prior art or solve certain deficiencies in the prior art. Those skilled in the art should be aware of this flexibility.

[0053] See also Figure 2 In one embodiment, the hemodialysis bubble detection device of the present application comprises:

[0054] An injection device, the injection device is connected to the blood circulation device, and comprises a plurality of injection pumps and a check valve, and blood is injected into the blood circulation device through the injection pump;

[0055] The blood circulation device comprises a sealed container and a heater, wherein the sealed container is used to store the blood to be tested, and the heater is used to stir the blood to simulate blood flow and heat the blood to maintain the temperature of the blood to be tested;

[0056] The bubble detection device is connected to the blood circulation device, and comprises a test pipeline, various pipeline control valves and a camera. The corresponding test pipeline for storing the blood to be tested is selected by controlling the pipeline control valve, and the camera is used to obtain image data of the blood to be tested in the test pipeline;

[0057] A central processing module is connected to the camera and is used to input the image data of the blood to be tested into the hemodialysis bubble detection module of the central processing module to detect the volume of the hemodialysis bubbles of the blood to be tested in the test pipeline.

[0058] Specifically, see Figure 1 as well as Figure 2 The hemodialysis bubble detection device comprises: an injection device, a blood circulation device, a bubble detection device and a central processing module. Specifically, the injection device comprises a first injection pump 1 and a first check valve corresponding thereto and a second injection pump 2 and a second check valve corresponding thereto. The first injection pump 1 and the first check valve corresponding thereto and the second injection pump 2 and the second check valve corresponding thereto are respectively connected to the blood circulation pipeline;

[0059] The blood circulation device includes a closed container 3 and a heater 4; the bubble detection device includes a pipeline control valve 5, a test pipeline 6 and a camera 7, the camera 7 is connected to the central processing module, the central processing module includes a hemodialysis bubble detection module, wherein the hemodialysis bubble detection module is configured with a hemodialysis bubble detection model, and the central processing module is a computer.

[0060] In some embodiments, the injection device includes a first injection pump and a second injection pump, the first injection pump is used to inject air, and the second injection pump is used to inject dialysate and anticoagulant.

[0061] The air flow control range of the first injection pump 1 and the second injection pump 2 is set between 0.2ml / min and 2.0ml / min, and the adjustable step is at least 0.1ml / min, and the error is controlled within ±3%. This design allows the experimenter to perform precise flow adjustment according to the experimental requirements to ensure the consistency and repeatability of the experimental conditions;

[0062] In some embodiments, an interface is left at the end of the first injection pump 1 and connected to a 22G puncture needle. This design allows the injection pump to be easily connected to different experimental equipment. At the same time, the replaceability of the 22G puncture needle provides additional flexibility and convenience, and puncture needles of different specifications can be replaced according to different experimental requirements or patient conditions, thereby improving the applicability and safety of the system.

[0063] In some embodiments, the bubble detection device includes four test pipes and two cameras, the first test pipe and the second test pipe are a first group of test pipes, and the third test pipe and the fourth test pipe are a second group of test pipes, wherein the test pipes are equipped with pipe control valves, the upper and lower valves of each group of test pipes are linked and controlled, and each camera shoots two test pipes in the same group.

[0064] The test pipeline 6 is kept 90 degrees vertical to the support platform. This vertical configuration helps to reduce parallax errors caused by pipeline tilt. At the same time, the support platform is equipped with a level gauge, which can provide real-time visual feedback when placing the test pipeline, ensuring that the pipeline is completely vertical during the measurement process, thereby minimizing measurement errors.

[0065] In some embodiments, the camera 7 is disposed on a fixed bracket and is provided with a positioning mechanism module to ensure that the relative position and angle between the camera and the test pipeline remain unchanged during the shooting process.

[0066] Specifically, the fixing bracket of the camera 7 is placed at a horizontal position of the test pipe 6. The design of the fixing bracket ensures that the relative position and angle between the camera and the test pipe remain consistent during each measurement, which helps to maintain the consistency and repeatability of image capture;

[0067] In some embodiments, the hemodialysis bubble detection device further includes: an alarm module, which is used to send a blood bubble excessive warning to the display module when it detects that the volume of bubbles in the blood to be detected is greater than a preset volume threshold.

[0068] In some embodiments, the hemodialysis bubble detection module includes: a region segmentation module, which is used to select the region of interest of the blood to be detected in the test pipeline; a binarization processing module, which is used to screen out the contour corresponding to the hemodialysis bubble in the image of the region of interest; a corrosion processing module, which is used to remove non-bubble intervention factors in the contour corresponding to the hemodialysis bubble; an expansion processing module, which is used to fill the holes in the edge of the contour corresponding to the hemodialysis bubble to ensure that the area containing the hemodialysis bubble is completely selected; a minimum circumscribed matrix generation module, which is used to generate the minimum circumscribed rectangle of the area containing the hemodialysis bubble; an edge detection module, which is used to determine the upper boundary edge point and the lower boundary edge point of the minimum circumscribed rectangle, and connect the detected edge points into a line to determine the upper boundary and the lower boundary of the hemodialysis bubble accumulation; a bubble volume determination module, which is used to determine the accumulation height of the hemodialysis bubble in the test pipeline according to the maximum value of the ordinate in the lower boundary edge point of the minimum circumscribed rectangle and the minimum value of the ordinate in the upper boundary edge point, and determine the volume of the hemodialysis bubble based on the accumulation height and the specific specifications of the test pipeline.

[0069] In some embodiments, the cleaning function of the system is taken into consideration, and the system pipeline is subjected to a strict water pressure test during design to verify that it can withstand a water pressure of 0.1 to 0.3 MPa without leakage, thereby ensuring the integrity of the pipeline. The pipeline design needs to be smooth inside without dead corners to facilitate the complete removal of residues during the cleaning process. In addition, the system is designed with a replaceable connector to facilitate connection with tap water or pure water systems, so as to achieve quick and convenient cleaning of the pipeline.

[0070] The working principle of the hemodialysis bubble detection device of the present application is as follows: the blood to be detected first flows at a constant temperature in the blood circulation device to simulate the liquid injection process in hemodialysis. According to the experimental requirements, a corresponding injection pump is selected to inject substances such as air or dialysate into the blood circulation device. Subsequently, the blood to be detected flows into the bubble detection device, where the camera 7 captures the blood image in the test line 6. The captured image is then transmitted to the connected computer system, and the hemodialysis bubble detection model running in the computer will detect and analyze these blood images.

[0071] Specifically, see Figure 3 The detailed working process of the hemodialysis bubble detection device of the present application includes the following steps:

[0072] Step S101, storing blood: In the blood circulation device, the blood to be tested is placed in a dedicated closed container 3, and the blood is properly stirred and heated by the built-in heater 4 to simulate the in vivo environment and maintain the fluidity of the blood;

[0073] In some embodiments, the designed blood circulation device uses highly biocompatible materials, while ensuring that all parts of the device are sealed to minimize the impact on the natural components of blood during blood storage and transportation.

[0074] In some embodiments, in order to maintain the stability of the blood, the heater is set to simulate the temperature of the human body, which can prevent the blood from coagulating at too low a temperature and ensure the activity and safety of the blood components.

[0075] In some embodiments, the stirring mechanism in the blood circulation device is designed to perform uniform stirring, thereby preventing the blood from being damaged by excessive stirring and also preventing unnecessary sedimentation of blood components.

[0076] Step S102, injection operation: according to the system setting or experimental requirements, the first injection pump 1 or the second injection pump 2 is selected to inject air or diluent or other substances into the blood circulation device. After the injection operation is completed, the corresponding first check valve or the second check valve is immediately started to prevent the gas and liquid from flowing back in the system;

[0077] In some embodiments, the designed syringe pump can accurately adjust the injection rate and volume to meet the needs of different experimental conditions.

[0078] In some embodiments, the syringe pump has a reversible peristaltic function, which can effectively control the injection of gas under negative pressure conditions, thereby preventing air from entering the blood circulation device in an uncontrolled manner.

[0079] In some embodiments, the check valve used in conjunction with the injection pump adopts a high-sensitivity sensing mechanism to ensure that it can be closed in time after the injection of the injection pump is completed, preventing any form of liquid or gas from flowing back, and ensuring the one-way flow of fluid inside the blood circulation device.

[0080] In some embodiments, the structural design of the check valve takes into account biocompatibility and durability to accommodate frequent operations and long-term use.

[0081] Step S103, blood distribution: The blood to be tested is first heated and stirred in the closed container 3 to maintain its appropriate temperature and fluidity. Subsequently, the blood to be tested flows into the bubble detection device through the connected pipeline. In the bubble detection device, the blood to be tested is distributed to the test pipeline 6 through the linkage control of the pipeline control valve 5. Specifically, two test pipelines are selected as a group each time they are distributed. For example, the first test pipeline and the second test pipeline are the first group of test pipelines, and the third test pipeline and the fourth test pipeline are the second group of test pipelines, wherein the test pipelines are equipped with pipeline control valves, and the upper and lower valves of each group of test pipelines are linkage controlled, and each camera shoots two test pipelines in the same group to ensure that the blood in these two pipelines can be tested at the same time.

[0082] In some embodiments, the pipeline control valve 5 is designed to be operated automatically and remotely controlled by computer software. At the same time, the selected test pipeline in the software interface will light up as a reminder;

[0083] In some embodiments, the design of the test line 6 takes into account the need for continuous blood flow. It is not only able to withstand continuous blood flow, but also is designed to provide a clear visual window so that the camera 7 in the bubble detection device can capture clear images.

[0084] In some embodiments, in order to remotely control the pipeline control valve in the bubble detection device, automatic control is achieved through the STM32 microcontroller. It is not difficult to understand that the pipeline control valve in the bubble detection device can also be remotely controlled by other means, which is not limited here.

[0085] Step S104, image capture: In the bubble detection device, the camera 7 is fixed at a calibrated position. When the blood to be detected flows in the test tube 6, the camera 7 captures the blood to be detected through the test tube, and then transmits the captured image to the computer system through the data transmission interface;

[0086] In some embodiments, the camera 7 is fixed in a precisely calibrated position in the bubble detection device through a fixed bracket and a positioning mechanism to ensure that each shot can obtain images under the same viewing angle and lighting conditions. This calibration process not only takes into account the position of the camera, but also comprehensively considers the layout of the internal lighting system and the light projection angle to ensure that the blood to be tested is illuminated uniformly and without glare when flowing in the test tube 6.

[0087] In some embodiments, to improve image quality, the device is equipped with a precisely controlled lighting system, which not only ensures uniform and glare-free lighting, but also combines with the aforementioned camera position calibration to optimize image contrast and clarity.

[0088] In some embodiments, the camera 7 has an autofocus function and can automatically adjust the focus according to the position of the hemodialysis bubble to be detected, ensuring that the bubble edge in the image is clearly discernible.

[0089] Step S105, bubble detection: First, the camera 7 captures an image of the blood to be tested in the test tube 6, and then transmits the image to the hemodialysis bubble detection model on the computer side. The software is responsible for image analysis to accurately detect and quantify the bubble content;

[0090] In some embodiments, the hemodialysis bubble detection model adopts a multi-module design, including modules such as region segmentation, binarization processing, corrosion and expansion processing, minimum circumscribed rectangle generation and edge detection, so as to achieve accurate screening and quantification of the bubble area.

[0091] In some embodiments, the hemodialysis bubble detection device also includes an early warning module. Once it is detected that the bubble volume exceeds the safety threshold, the early warning module will promptly issue a warning and suspend the dialysis process; once the early warning module in the hemodialysis bubble detection device detects an abnormal situation, such as the bubble volume exceeds the preset safety threshold, the system will immediately start the alarm program to ensure that the operator is warned in time. Specifically, a flashing red light will be displayed on the display module in the hemodialysis bubble detection device, which is a visual signal used to quickly attract the attention of the operator. At the same time, the pipeline control valve 5 will be closed synchronously, thereby cutting off the flow of liquid in the test pipeline to ensure the safety of the treatment process.

[0092] As can be seen from the above embodiments, compared with the prior art, the present application aims at the problem that bubbles generated in blood purification treatment in the prior art may cause various complications including gas embolism and vascular blockage, which pose a serious threat to the health and safety of patients. The present application includes but is not limited to the following beneficial effects:

[0093] First, the hemodialysis bubble detection device of the present application is mainly composed of an injection device, a blood circulation device, a bubble detection device and a central processing module. It cooperates with the hemodialysis bubble detection model in the central processing module to work together to complete the detection and analysis of bubbles. The present application significantly improves the accuracy and efficiency of bubble detection in hemodialysis treatment and ensures the life safety of patients. The hemodialysis bubble detection device realizes the accurate identification and measurement of bubbles in the blood to be tested through the designed injection device, blood circulation device, bubble detection device and computer. The hemodialysis bubble detection device adopts image recognition technology, and effectively screens and quantifies the bubble area from the blood image to be tested through the modules such as region segmentation, binarization processing, corrosion and expansion processing, minimum circumscribed rectangle generation and edge detection in the hemodialysis bubble detection model. In addition, the built-in calibration module of the hemodialysis bubble detection device ensures the high accuracy of bubble volume measurement, and the design of the early warning module promptly issues an alarm and interrupts the detection process when the bubble volume exceeds the standard, thereby effectively avoiding possible medical risks.

[0094] Secondly, the hemodialysis bubble detection method of the present application adopts a multi-module design, and performs operations such as region segmentation, binarization processing, corrosion and expansion processing, minimum circumscribed rectangle generation and edge detection to accurately identify and quantify the bubble area. By identifying and quantifying the bubble area, the volume of the hemodialysis bubble in the test pipeline is determined to avoid the occurrence of safety accidents caused by excessive hemodialysis bubbles and avoid endangering the life safety of patients.

[0095] On the basis of any of the above embodiments, in the hemodialysis bubble detection model, the received blood image to be detected is uploaded to the central processing module, and the hemodialysis bubble detection model in the central processing module performs the following operations:

[0096] The region segmentation is performed to select the region of interest (ROI), and then the bubble region is initially screened out through binarization processing, and then erosion and expansion processing are performed to remove interference factors and ensure the integrity of the bubble region. The system further identifies the minimum enclosing rectangle of the bubble region and performs edge detection to determine the accumulation boundary of the bubble; by calculating the maximum and minimum values ​​of the vertical coordinate of the bubble accumulation height, combined with the pixel physical size of the camera photo, the volume of the bubble can be obtained.

[0097] A hemodialysis bubble detection method provided to meet one of the purposes of the present application is applied to the above-mentioned hemodialysis bubble detection device, comprising:

[0098] Step S1100: the central processing module acquires the blood image to be detected, and performs region segmentation based on the hemodialysis bubble detection model preset in the hemodialysis bubble detection module to determine the region of interest in the blood image to be detected;

[0099] When the camera 7 in the hemodialysis bubble detection device captures the blood image to be detected in the test tube 6, the central processing module obtains the blood image to be detected, and performs region segmentation based on the hemodialysis bubble detection model preset in the hemodialysis bubble detection module in the central processing module to determine the region of interest in the blood image to be detected;

[0100] Specifically, the hemodialysis bubble detection model preset in the hemodialysis bubble detection module receives the blood image to be detected taken and uploaded by the camera, and then the software directly uses the ROI tool to accurately select the region of interest of the blood to be detected in the test tube. This process is the basis for subsequent image processing and bubble analysis, and provides the necessary prerequisite for achieving accurate bubble detection;

[0101] The blood image to be detected received by the hemodialysis bubble detection model contains hemodialysis bubbles, mixed liquids such as blood and diluent, and a test tube, so it is necessary to separate them through the above steps to only take the images of the liquid and bubbles;

[0102] In some embodiments, in order to ensure the accuracy of image analysis, this step requires that during each detection process, the camera's shooting angle and the relative position of the test tube must remain constant, and at the same time, the lighting conditions should also be maintained in a relatively stable state.

[0103] Step S1200, determining a preset grayscale threshold, and dividing the image pixels corresponding to the region of interest in the blood image to be detected into a foreground and a background according to the preset grayscale threshold, so as to determine the contour corresponding to the hemodialysis bubble, wherein the foreground represents the hemodialysis bubble, and the background represents the blood and the dialysate;

[0104] After determining the region of interest in the blood image to be detected, determining a preset grayscale threshold, and dividing the image pixels corresponding to the region of interest in the blood image to be detected into a foreground and a background according to the preset grayscale threshold, so as to determine the contour corresponding to the hemodialysis bubble, wherein the foreground represents the hemodialysis bubble, and the background represents the blood and the dialysate;

[0105] Specifically, a suitable preset grayscale threshold is determined to distinguish the foreground from the background, wherein the foreground represents the hemodialysis bubbles and the background represents the blood and the dialysate; after the preset grayscale threshold is determined, the hemodialysis bubble detection model will evaluate each pixel in the image, and each pixel point is classified into one of two colors: black or white according to the comparison result of its grayscale value with the set threshold, wherein white represents the foreground, i.e., the bubble area, and black represents the background, including blood and the dialysate;

[0106] It can be seen from the above embodiments that the hemodialysis bubble detection model adopts an adaptive threshold method to determine the threshold used in image processing to achieve more accurate separation of bubbles and blood. The adaptive threshold method calculates the threshold according to the local characteristics of the image, taking into account factors such as uneven illumination, different bubble sizes, and background changes that may exist in the image, so that each local area can be binarized using the most appropriate threshold;

[0107] In other embodiments, the threshold may be selected by a global threshold, an Otsu method based on image histogram statistics, or the like, which is not limited here.

[0108] Step S1300, performing erosion and expansion operations on the contour corresponding to the hemodialysis bubble to eliminate small white noise points in the image and fill the holes at the edge of the bubble to determine the hemodialysis bubble area image;

[0109] The image pixels corresponding to the region of interest in the blood image to be detected are divided into foreground and background according to the preset grayscale threshold, and after the contour corresponding to the hemodialysis bubble is determined, the contour corresponding to the hemodialysis bubble is corroded and expanded to eliminate small white noise points in the image and fill the holes at the edge of the bubble to determine the hemodialysis bubble area image;

[0110] Specifically, the contour corresponding to the hemodialysis bubble is corroded and expanded. After the hemodialysis bubble is successfully separated by binarization, the corrosion operation is performed to remove small white noise points in the image that may cause misjudgment. Furthermore, the continuity of the bubble edge is enhanced through the expansion operation, so that the area containing the bubble is selected more completely, which is convenient for subsequent edge detection and bubble shape analysis.

[0111] It can be seen from the above embodiments that the random noise in the image is reduced by the corrosion operation, which helps to effectively separate the bubble area from the blood part in the background. The edge of the bubble area is made clearer and more coherent by the expansion operation, which helps to form a complete bubble outline. Through these processing steps, the characteristics of the bubble in the image are significantly enhanced, and the background noise is effectively suppressed, ensuring that the software can accurately identify and quantify the bubble from the complex image background.

[0112] Step S1400, calculating and determining the minimum circumscribed rectangle corresponding to the hemodialysis bubble area image, and generating a virtual caliper for measuring boundary edge points;

[0113] After determining the hemodialysis bubble area image, calculating and determining the minimum circumscribed rectangle corresponding to the hemodialysis bubble area image, and generating a virtual caliper for measuring boundary edge points;

[0114] In some embodiments, the step of calculating and determining the minimum circumscribed rectangle corresponding to the hemodialysis bubble area image and generating a virtual caliper for measuring boundary edge points includes:

[0115] Step S14001: determining the minimum circumscribed matrix corresponding to the bubble region based on the bubble region image, and using the upper boundary and the lower boundary of the minimum circumscribed matrix as reference edges, which correspond to the upper boundary and the lower boundary of the hemodialysis bubble respectively;

[0116] Step S14003: Generate a number of rectangular handles along the reference edge, and use the rectangular handles as virtual calipers to identify and measure edge points on the upper and lower boundaries of the hemodialysis bubble.

[0117] Specifically, a minimum circumscribed rectangle corresponding to the hemodialysis bubble area image is generated. The hemodialysis bubble area image is identified through the above operation, and the hemodialysis bubble detection model calculates the minimum circumscribed matrix of the area, and uses the upper boundary and the lower boundary of the minimum circumscribed matrix as a reference, which correspond to the upper boundary and the lower edge of the hemodialysis bubble respectively. Along these two reference edges, the hemodialysis bubble detection model generates a number of rectangular handles, which serve as virtual "measuring calipers", that is, virtual calipers, for identifying and measuring edge points on the bubble boundary.

[0118] Step S1500, determining the ordinates of the lower boundary edge points and the upper boundary edge points corresponding to the minimum circumscribed rectangle based on the virtual caliper, calculating and determining the difference between the maximum ordinate of the lower boundary edge points and the minimum ordinate of the upper boundary edge points corresponding to the minimum circumscribed rectangle, and determining the stacking height of the hemodialysis bubbles in the test pipeline according to the difference;

[0119] After calculating and determining the minimum circumscribed rectangle corresponding to the hemodialysis bubble area image and generating a virtual caliper for measuring the boundary edge points, the vertical coordinates of the lower boundary edge points and the vertical coordinates of the upper boundary edge points corresponding to the minimum circumscribed rectangle are determined based on the virtual caliper, the difference between the maximum vertical coordinates of the lower boundary edge points and the minimum vertical coordinates of the upper boundary edge points corresponding to the minimum circumscribed rectangle are calculated and determined, and the stacking height of the hemodialysis bubble in the test pipeline is determined according to the difference;

[0120] In some embodiments, after the step of generating a plurality of rectangular handles along the reference edge and using the rectangular handles as virtual calipers to identify and measure edge points on the upper and lower boundaries of the hemodialysis bubble, the method further comprises:

[0121] The virtual caliper identifies and measures the edge points on the upper and lower boundaries of the blood bubble, and stores the edge points in an array, in which a search is performed to identify the minimum value of the vertical coordinate among all the upper boundary edge points and the maximum value of the vertical coordinate among all the lower boundary edge points.

[0122] Specifically, the hemodialysis bubble detection model determines the edge points corresponding to the minimum circumscribed rectangle through the virtual caliper measurement, and stores these edge points in an array. Subsequently, the hemodialysis bubble detection model searches in the array to identify the minimum value of the longitudinal coordinate among all upper boundary edge points and the maximum value of the longitudinal coordinate among all lower boundary edge points.

[0123] Step S1600: Based on the stacking height of the hemodialysis bubbles in the test pipeline and the specific specifications of the test pipeline, the volume of the hemodialysis bubbles is calculated to complete the detection of the hemodialysis bubbles.

[0124] After determining the stacking height of the hemodialysis bubbles in the test pipeline according to the difference, the volume of the hemodialysis bubbles is calculated and determined based on the stacking height of the hemodialysis bubbles in the test pipeline and the specific specifications of the test pipeline to complete the detection of the hemodialysis bubbles.

[0125] Specifically, the bubble detection model determines the accumulation height of the hemodialysis bubbles in the test tube by calculating the difference between the maximum value of the ordinate of the lower boundary edge point of the bubble and the minimum value of the ordinate of the upper boundary edge point. With the accumulation height of the hemodialysis bubbles in the test tube, the hemodialysis bubble detection model can further calculate the volume of the hemodialysis bubbles based on the specific specifications of the test tube and the accumulation height of the hemodialysis bubbles in the test tube.

[0126] In some embodiments, after the step of calculating and determining the volume of the hemodialysis bubbles based on the stacking height of the hemodialysis bubbles in the test line and the specific specifications of the test line, the method includes:

[0127] In response to the alarm detection instruction, the volume of the hemodialysis bubble is obtained, and whether the volume of the hemodialysis bubble exceeds the preset volume threshold is detected. If exceeded, a bubble excessive warning signal is pushed to the display module to emit a flashing red light, and the pipeline control valve is controlled to be closed to cut off the blood circulation in the test pipeline to ensure the safety of the treatment process.

[0128] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

[0129] In summary, it can be seen from the above embodiments that, compared with the prior art, the present application aims at the problem that bubbles generated in blood purification treatment in the prior art may cause various complications including gas embolism and vascular blockage, which pose a serious threat to the health and safety of patients. The present application includes but is not limited to the following beneficial effects:

[0130] First, the hemodialysis bubble detection device of the present application is mainly composed of an injection device, a blood circulation device, a bubble detection device and a central processing module. It cooperates with the hemodialysis bubble detection model in the central processing module to work together to complete the detection and analysis of bubbles. The present application significantly improves the accuracy and efficiency of bubble detection in hemodialysis treatment and ensures the life safety of patients. The hemodialysis bubble detection device realizes the accurate identification and measurement of bubbles in the blood to be tested through the designed injection device, blood circulation device, bubble detection device and computer. The hemodialysis bubble detection device adopts image recognition technology, and effectively screens and quantifies the bubble area from the blood image to be tested through the modules such as region segmentation, binarization processing, corrosion and expansion processing, minimum circumscribed rectangle generation and edge detection in the hemodialysis bubble detection model. In addition, the built-in calibration module of the hemodialysis bubble detection device ensures the high accuracy of bubble volume measurement, and the design of the early warning module promptly issues an alarm and interrupts the detection process when the bubble volume exceeds the standard, thereby effectively avoiding possible medical risks.

[0131] Secondly, the hemodialysis bubble detection method of the present application adopts a multi-module design, and performs operations such as region segmentation, binarization processing, corrosion and expansion processing, minimum circumscribed rectangle generation and edge detection to accurately identify and quantify the bubble area. By identifying and quantifying the bubble area, the volume of the hemodialysis bubble in the test pipeline is determined to avoid the occurrence of safety accidents caused by excessive hemodialysis bubbles and avoid endangering the life safety of patients.

Claims

1. A hemodialysis bubble detection device, characterized in that: include An injection device, the injection device is connected to the blood circulation device, and comprises a plurality of injection pumps and a check valve, and blood is injected into the blood circulation device through the injection pump; The blood circulation device comprises a sealed container and a heater, wherein the sealed container is used to store the blood to be tested, and the heater is used to stir the blood to simulate blood flow and heat the blood to maintain the temperature of the blood to be tested; The bubble detection device is connected to the blood circulation device, and comprises a test pipeline, various pipeline control valves and a camera. The corresponding test pipeline for storing the blood to be tested is selected by controlling the pipeline control valve, and the camera is used to obtain image data of the blood to be tested in the test pipeline; A central processing module is connected to the camera and is used to input the image data of the blood to be tested into the hemodialysis bubble detection module of the central processing module to detect the volume of the hemodialysis bubbles of the blood to be tested in the test pipeline.

2. The hemodialysis bubble detection device according to claim 1, characterized in that: The injection device comprises a first injection pump and a second injection pump, the first injection pump is used to inject air, and the second injection pump is used to inject dialysate and anticoagulant.

3. The hemodialysis bubble detection device according to claim 1, characterized in that: The bubble detection device includes four test pipelines and two cameras, the first test pipeline and the second test pipeline are the first group of test pipelines, and the third test pipeline and the fourth test pipeline are the second group of test pipelines, wherein the test pipelines are equipped with pipeline control valves, the upper and lower valves of each group of test pipelines are linked and controlled, and each camera shoots two test pipelines in the same group.

4. The hemodialysis bubble detection device according to claim 3, characterized in that: The camera is arranged on a fixed bracket and is provided with a positioning mechanism module to ensure that the relative position and angle between the camera and the test pipeline remain unchanged during the shooting process.

5. The hemodialysis bubble detection device according to claim 1, characterized in that: The hemodialysis bubble detection device further comprises: The alarm module is used to send a blood bubble excessively large warning to the display module when it detects that the volume of bubbles in the blood to be detected is greater than a preset volume threshold.

6. The hemodialysis bubble detection device according to claim 1, characterized in that: The hemodialysis bubble detection module comprises: A region segmentation module, which is used to select a region of interest of the blood to be tested in the test tube; A binarization processing module, which is used to filter out the contours corresponding to the hemodialysis bubbles in the image of the region of interest; A corrosion processing module, which is used to remove non-bubble intervention factors within the contour corresponding to the hemodialysis bubble; An expansion processing module, which is used to fill the hole at the edge of the contour corresponding to the hemodialysis bubble to ensure that the area containing the hemodialysis bubble is completely selected; A minimum circumscribed matrix generation module, which is used to generate a minimum circumscribed rectangle of an area containing the hemodialysis bubble; An edge detection module, which is used to determine the upper boundary edge point and the lower boundary edge point of the minimum circumscribed rectangle, and connect the detected edge points into lines to determine the upper boundary and the lower boundary of the hemodialysis bubble accumulation; A bubble volume determination module is used to determine the stacking height of the hemodialysis bubbles in the test pipeline according to the maximum value of the ordinate in the lower boundary edge point of the minimum circumscribed rectangle and the minimum value of the ordinate in the upper boundary edge point, and determine the volume of the hemodialysis bubbles based on the stacking height and the specific specifications of the test pipeline.

7. A method for detecting hemodialysis bubbles, applied to the hemodialysis bubble detection device according to any one of claims 1 to 6, characterized in that: Also includes: The central processing module acquires the blood image to be detected, and performs region segmentation based on the hemodialysis bubble detection model preset in the hemodialysis bubble detection module to determine the region of interest in the blood image to be detected; Determine a preset grayscale threshold, and divide the image pixels corresponding to the region of interest in the blood image to be detected into a foreground and a background according to the preset grayscale threshold, so as to determine the contour corresponding to the hemodialysis bubble, wherein the foreground represents the hemodialysis bubble, and the background represents the blood and the dialysate; Performing erosion and expansion operations on the contour corresponding to the hemodialysis bubble to eliminate small white noise points in the image and fill the holes at the edge of the bubble to determine the hemodialysis bubble area image; Calculating and determining the minimum circumscribed rectangle corresponding to the hemodialysis bubble area image, and generating a virtual caliper for measuring boundary edge points; Determine the ordinates of the lower boundary edge points and the upper boundary edge points corresponding to the minimum circumscribed rectangle based on the virtual caliper, calculate and determine the difference between the maximum ordinate of the lower boundary edge points and the minimum ordinate of the upper boundary edge points corresponding to the minimum circumscribed rectangle, and determine the stacking height of the hemodialysis bubbles in the test pipeline according to the difference; Based on the stacking height of the hemodialysis bubbles in the test pipeline and the specific specifications of the test pipeline, the volume of the hemodialysis bubbles is calculated and determined to complete the detection of the hemodialysis bubbles.

8. The hemodialysis bubble detection method according to claim 7, characterized in that: After the step of calculating and determining the volume of the hemodialysis bubbles based on the stacking height of the hemodialysis bubbles in the test pipeline and the specific specifications of the test pipeline, the method includes: In response to the alarm detection instruction, the volume of the hemodialysis bubble is obtained, and whether the volume of the hemodialysis bubble exceeds the preset volume threshold is detected. If exceeded, a bubble excessive warning signal is pushed to the display module to emit a flashing red light, and the pipeline control valve is controlled to be closed to cut off the blood circulation in the test pipeline to ensure the safety of the treatment process.

9. The hemodialysis bubble detection method according to claim 7, characterized in that: The steps of calculating and determining the minimum circumscribed rectangle corresponding to the hemodialysis bubble area image and generating a virtual caliper for measuring boundary edge points include: Determine the minimum circumscribed matrix corresponding to the bubble area based on the bubble area image, and use the upper boundary and the lower boundary of the minimum circumscribed matrix as reference edges, which correspond to the upper boundary and the lower boundary of the hemodialysis bubble respectively; A plurality of rectangular handles are generated along the reference edge, and the rectangular handles are used as virtual calipers to identify and measure edge points on the upper and lower boundaries of the hemodialysis bubble.

10. The hemodialysis bubble detection method according to claim 9, characterized in that: After the step of generating a plurality of rectangular handles along the reference edge and using the rectangular handles as virtual calipers to identify and measure edge points on the upper and lower boundaries of the hemodialysis bubble, the method includes: The virtual caliper identifies and measures the edge points on the upper and lower boundaries of the blood bubble, and stores the edge points in an array, in which a search is performed to identify the minimum value of the vertical coordinate among all the upper boundary edge points and the maximum value of the vertical coordinate among all the lower boundary edge points.

Citation Information

Patent Citations

  • Bubble detection device and bubble detection method based on light refraction and reflection

    CN114897871A

  • Optical imaging system for air bubble and empty bag detection in an infusion tube

    US20130201471A1

Cited By

  • Dual-channel air monitoring system for dialysis

    CN122376897A

  • Method and device for characterising an air sensor in an extracorporeal blood treatment device

    WO2026154122A1

  • Processing device, extracorporeal circulation system, processing method, program, and storage medium

    WO2026204207A1